Class PostgresDocumentSaver (0.7.0)

PostgresDocumentSaver(
    key,
    engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
    table_name: str,
    content_column: str,
    metadata_columns: typing.List[str] = [],
    metadata_json_column: typing.Optional[str] = None,
)

A class for saving langchain documents into a PostgreSQL database table.

Methods

PostgresDocumentSaver

PostgresDocumentSaver(
    key,
    engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
    table_name: str,
    content_column: str,
    metadata_columns: typing.List[str] = [],
    metadata_json_column: typing.Optional[str] = None,
)

PostgresDocumentSaver constructor.

Parameters
Name	Description
`key`	`object` Prevent direct constructor usage.
`engine`	`PostgresEngine` AsyncEngine with pool connection to the postgres database
`table_name`	`Optional[str], optional` Name of table to query. Defaults to None.
`content_columns`	`Optional[List[str]], optional` Column that represent a Document's page_content. Defaults to the first column.
`metadata_columns`	`Optional[List[str]], optional` Column(s) that represent a Document's metadata. Defaults to None.
`metadata_json_column`	`Optional[str], optional` Column to store metadata as JSON. Defaults to "langchain_metadata".

Exceptions
Type	Description
`Exception`	if called directly by user.

_aload_table_schema

_aload_table_schema() -> sqlalchemy.sql.schema.Table

Load table schema from existing table in PgSQL database.

Returns
Type	Description
`(sqlalchemy.Table)`	The loaded table.

aadd_documents

aadd_documents(docs: typing.List[langchain_core.documents.base.Document]) -> None

Save documents in the DocumentSaver table. Document’s metadata is added to columns if found or stored in langchain_metadata JSON column.

Parameter
Name	Description
`docs`	`List[langchain_core.documents.Document]` a list of documents to be saved.

add_documents

add_documents(docs: typing.List[langchain_core.documents.base.Document]) -> None

Save documents in the DocumentSaver table. Document’s metadata is added to columns if found or stored in langchain_metadata JSON column.

Parameter
Name	Description
`docs`	`List[langchain_core.documents.Document]` a list of documents to be saved.

adelete

adelete(docs: typing.List[langchain_core.documents.base.Document]) -> None

Delete all instances of a document from the DocumentSaver table by matching the entire Document object.

Parameter
Name	Description
`docs`	`List[langchain_core.documents.Document]` a list of documents to be deleted.

create

create(
    engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[str] = [],
    metadata_json_column: typing.Optional[str] = "langchain_metadata",
)

Create an PostgresDocumentSaver instance.

Parameters
Name	Description
`engine`	`PostgresEngine` AsyncEngine with pool connection to the postgres database
`table_name`	`Optional[str], optional` Name of table to query. Defaults to None.
`content_columns`	`Optional[List[str]], optional` Column that represent a Document's page_content. Defaults to the first column.
`metadata_columns`	`Optional[List[str]], optional` Column(s) that represent a Document's metadata. Defaults to None.
`metadata_json_column`	`Optional[str], optional` Column to store metadata as JSON. Defaults to "langchain_metadata".

create_sync

create_sync(
    engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[str] = [],
    metadata_json_column: str = "langchain_metadata",
)